There are many active research projects accessing and applying shared ADNI data. Use the search above to find specific research focuses on the active ADNI investigations. This information is requested annually as a requirement for data access.
| Principal Investigator | |
| Principal Investigator's Name: | Liqing Zhu |
| Institution: | University of Electronic Science and Technology of China |
| Department: | biomedical engineering |
| Country: | |
| Proposed Analysis: | The data from this application will be used for my graduation design, titled: Machine Learning Based Identification of Alzheimer's Disease Subtypes. The aim of this project is to characterize AD subtypes by deep clustering of AD pathotype data. The ultimate goal is to deepen our understanding of the mechanisms driving heterogeneity among different subtypes of AD and to find a regular cognition of possible phenotypes and classifications that will hopefully contribute to current research in precision medicine and promote specific treatments. This project plans to use a clustering algorithm to typify AD. The Python platform was chosen for the development environment. The data source requires the AD phenotype database provided by ADNI, mainly fMRI data, so this application was made. This project proposes to use deep clustering algorithms, such as deep K-means or deep GMM clustering algorithms, combining feature learning with clustering, where clustering leads to a better feature space, and the low-level feature space obtained from the same genus of deep learning can be further clustered. The clusters obtained by clustering are then further subjected to cluster analysis to obtain different typologies of AD. I sincerely hope that you can pass my application, and I wish you good luck in your work and happy family! |
| Additional Investigators |
